© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14368
    Prev
    Next
    INDEX
    Explanations

    custom mug or tote

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    going
    1.19
    ra
    1.19
    ح
    1.18
    bs
    1.18
    asmuch
    1.16
    ging
    1.15
    spre
    1.14
    ment
    1.12
    rable
    1.09
    »
    1.08
    POSITIVE LOGITS
     appContext
    1.74
    editText
    1.63
     centerY
    1.60
    ிலான
    1.58
     islamic
    1.57
     dinast
    1.56
     toasts
    1.54
    педи
    1.53
     版本
    1.52
     figurines
    1.50
    Activations Density 0.000%

    No Known Activations